query_local_llm · Local Llm Delegation MCP: Risk & Policy

WHAT IT DOES

What query_local_llm does on Local Llm Delegation

AI agents invoke query_local_llm to trigger actions in Local Llm Delegation. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why query_local_llm needs a policy

This tool executes a query against a local LLM, which runs an external computational process. While it doesn't directly delete data or move money, it executes model inference that could produce arbitrary outputs or consume resources.

From the tool's definition "Query the local LLM" - triggers execution of a language model inference operation with provided inputs

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

query_local_llm Rate-limited

query_local_llm stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "query_local_llm": {
      "limits": [
        {
          "counter": "query_local_llm_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Local Llm Delegation, so you can run agents against it safely.

FAQ

Questions about query_local_llm

What does the query_local_llm tool do? +

Query the local LLM for simple, well-defined subtasks that have already been broken down. It is categorised as a Execute tool in the Local Llm Delegation MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on query_local_llm? +

Register the Local Llm Delegation MCP server in PolicyLayer and add a rule for query_local_llm: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Local Llm Delegation. Nothing to install.

What risk level is query_local_llm? +

query_local_llm is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit query_local_llm? +

Yes. Add a rate_limit block to the query_local_llm rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block query_local_llm completely? +

Set action: deny in the PolicyLayer policy for query_local_llm. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides query_local_llm? +

query_local_llm is provided by the Local Llm Delegation MCP server (mrrodriguez/local-llm-delegation-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.